Bibliometrics of Machine Learning Research Using Homomorphic Encryption

Abstract

Since the first fully homomorphic encryption scheme was published in 2009, many papers have been published on fully homomorphic encryption and its applications. Machine learning is one of the most interesting applications and has drawn a lot of attention from researchers. To better represent and understand the field of Homomorphic Encryption in Machine Learning (HEML), this paper utilizes automated citation and topic analysis to characterize the HEML research literature over the years and provide the bibliometrics assessments for this burgeoning field. This is conducted by using a bibliometric statistical analysis approach. We make use of web-based literature databases and automated tools to present the development of HEML. This allows us to target several popular topics for in-depth discussion. To achieve these goals, we have chosen the well-established Scopus literature database and analyzed them through keyword counts and Scopus relevance searches. The results show a relative increase in the number of papers published each year that involve both homomorphic cryptography and machine learning. Using text mining of articles titles, we have found that cloud computing is a popular topic in this field, which also includes neural networks, big data, and the Internet of Things. The analysis results show that China, the US, and India have generated almost half of all the research contributions in HEML. The citation statistics, keyword statistics, and topic analyses give us a quick overview of the development of the field, which can be of great help to new researchers. It is also possible to apply our methodology to other research areas, and we see great value in this approach.

A Review of Homomorphic Encryption for Privacy-Preserving Biometrics

“…Given that the development of FHE in neural networks has shown significant progress in recent years, the authors focused on privacy-preserving homomorphic cryptosystems for neural networks, identifying current solutions, open problems, challenges, opportunities and future research. Chen et al [ 18 ] used a web-based literature database and automated tools to describe the development of HE in machine learning (HEML). Several hot topics of HEML (e.g., cloud computing) were discussed in detail.…”

HEProfiler: An In-Depth Profiler of Approximate Homomorphic Encryption Libraries

“…In this, we replace the max-pooling layers with average-pooling layers. Average-pooling is much easier to compute homomorphically than max-pooling; using average-pooling for FHE-based deep learning is common and has minimal loss of accuracy [81][82][83][84][85][86]. We used a degree-6 polynomial approximation of a ReLU activation function.…”

Application of Homomorphic Encryption in Machine Learning

“…We are interested therein Machine Learning Research Using Homomorphic Encryption "HEML". According to this Bibliometrics [11], the number of papers on HEML has constantly been rising since 2009. Each year from 2005 to 2015, fewer than 100 HEML papers were published.…”